作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2012, Vol. 38 ›› Issue (12): 129-131. doi: 10.3969/j.issn.1000-3428.2012.12.038

• 人工智能及识别技术 • 上一篇    下一篇

自然语料缺乏的民族语言连续语音识别

武晓敏 a,达瓦•伊德木草 a,b,吾守尔•斯拉木 a,b   

  1. (新疆大学 a. 信息科学与工程学院;b. 多语种信息技术重点实验室,乌鲁木齐 830046)
  • 收稿日期:2011-08-26 出版日期:2012-06-20 发布日期:2012-06-20
  • 作者简介:武晓敏(1986-),女,硕士研究生,主研方向:语音信号处理;达瓦?伊德木草,教授、博士;吾守尔?斯拉木,教授、博士生导师
  • 基金资助:

    国家自然科学基金资助面上项目(2011211A012, 608630 08);新疆维吾尔自治区科技支疆基金资助项目(201091106);博士启动基金资助项目(BS090144)

Continuous Speech Recognition for Natural Resource-deficient Minority Languages

WU Xiao-min a, Dawa•Idomuco a,b, Wushour•Silamu a,b   

  1. (a. College of Information Science and Engineering; b. Key Laboratory of Multilingual Information Technology, Xinjiang University, Urumqi 830046, China)
  • Received:2011-08-26 Online:2012-06-20 Published:2012-06-20

摘要: 以维吾尔语为例研究自然语料缺乏的民族语言连续语音识别方法。采用HTK通过人工标注的少量语料生成种子模型,引导大语音数据构建声学模型,利用palmkit工具生成统计语言模型,以Julius工具实现连续语音识别。实验用64个维语母语者自由发话的6 400个 短句语音建立单音素声学模型,由100 MB文本、6万词词典生成基于词类的3-gram语言模型,测试结果表明,该方法的识别率为 72.5%,比单用HTK提高4.2个百分点。

关键词: 连续语音识别, 种子模型, 声学模型, 语言模型, 维吾尔语

Abstract: This paper discusses a continuous speech recognition approach for the resource-deficient languages, such as Uyghur. This approach tries a seed acoustic model using small training speech materials and creates final acoustic model using a larger speech materials and its transcription text by leading seed model. HTK is used for training acoustic model, and palmkit is used for creating language model, and the open-source speech recognition software Julius is applied for continuous speech recognition. In the test, the speech data of 6 400 sentences uttered by 64 native Uyghur speakers is used for training acoustic model and 100 MB text materials and a dictionary of 60 000 words are used for creating 3-garm language model based class. Experimental results show the rate of 72.5% for the real time sound recognition compared with the recognition result of 68.3% by HTK tool only.

Key words: continuous speech recognition, seed model, acoustic model, language model, Uyghur

中图分类号: